Journal
2018 14TH INTERNATIONAL CONFERENCE ON MOBILE AD-HOC AND SENSOR NETWORKS (MSN 2018)
Volume -, Issue -, Pages 121-126Publisher
IEEE
DOI: 10.1109/MSN.2018.00027
Keywords
Trajectory data; Taxi route planning; Profit; Clustering algorithm; Heuristic algorithm
Categories
Funding
- Scientific and Technological Support Project of Jiangsu Province [BE2016776]
- 333 project of Jiangsu Province [BRA2017228]
- Talent Project in Six Fields of Jiangsu Province [2015-JNHB-012]
Ask authors/readers for more resources
Reasonable route planning for taxi can not only improve quality of customer experience, but also maximize the benefit of taxi drivers. Most current taxi planning schemes are designed to achieve the shortest route or the shortest time, not to achieve the best profit. In this paper, we propose a route planning scheme with best profit for taxi (RPSBPT). First, we define the optimal profit point and the profit per unit time function. Second, we design the workflow of data cleaning, sampling and partitioning for preprocessing the dataset of taxi trajectory. Then, we integrate the DBSCAN algorithm and the K-means algorithm to obtain the optimal profit points. Finally, the simulate anneal Algorithm (SA), the genetic algorithm (GA), and the ant colony optimization algorithm (ACO) are adopted respectively to plan route for taxi. We constructed the taxi route planning prototype system and applied the proposed route planning scheme to the system. Based on the system and the collected taxi trajectory data at the Jinjiang district of the Chengdu city, we performed a series of experiments to compare the performance of three heuristic algorithms, including optimal route length, algorithm stability, total profit and profitability per unit time. Experimental results show that ACO has the best performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available